Agentic AI Engineer

Tata Consultancy Services; Mumbai; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Tata Consultancy Services seeks an experienced AI Engineer to design and implement agentic workflows using LLMs, with emphasis on tool calls, memory, and orchestration across single/multi-agent setups.

The role requires strong MCP proficiency, RAG grounding, and monitoring via AgentOps, plus cloud-native deployment experience with Kubernetes/OpenShift and CI/CD practices. Proficiency in Python/Java/.NET is required.

Qualifications

• Strong understanding of agentic AI fundamentals.
• Design and implement agentic workflows using LLMs with tool calls, memory, and orchestration.
• Experience with LangChain-based frameworks or equivalents for routing and coordination.
• Proficiency with Model Context Protocol (MCP) for integrating tools and data.
• Ability to build Retrieval-Augmented Generation pipelines and grounding strategies.
• Experience with monitoring agent behavior and performance (AgentOps).
• Exposure to cloud/platform engineering with containers/Kubernetes/OpenShift, CI/CD.
• Awareness of Responsible AI, safety controls, and secure data handling.
• Proficiency in Python, .Net, or Java and related ML libraries (TensorFlow, PyTorch, Keras).

Responsibilities

• Design and build agentic workflows using LLMs, including tool calls and orchestration.
• Implement MCP-based tool integration and data routing.
• Develop RAG pipelines and grounding strategies for enterprise sources.
• Establish AgentOps observability with alerts and tracing.
• Deploy agentic systems in cloud environments with containers and CI/CD.
• Incorporate safe guardrails and human-in-the-loop controls.

Skills

Agentic AI fundamentals

LLM workflow design

Agent frameworks (LangChain)

MCP proficiency

RAG pipelines

AgentOps observability

Cloud/Kubernetes/OpenShift

Responsible AI & guardrails

Programming in Python/.NET/Java

Tools

LangChain frameworks

MCP servers

Kubernetes

CI/CD tooling

TensorFlow/PyTorch/Keras

Job description

Experience Range - 4 to 15 years

Job Description

• Strong understanding of agentic AI fundamentals—goal definition, planning, reasoning, task decomposition, and autonomous action loops.
• Design and build agentic workflows using LLMs, including tool/function calling, state management, memory, and orchestration patterns (single-agent/multi-agent).
• Hands-on experience with agent frameworks and patterns (e.g., LangChain-based agent frameworks or equivalents), including routing, workflows, and agent coordination.
• Model Context Protocol (MCP) proficiency for integrating tools and contextual data into agent workflows (tool discovery/usage via MCP servers).
• Build Retrieval-Augmented Generation (RAG) pipelines and grounding strategies for enterprise knowledge sources (e.g., internal repos/wikis/ticketing/content stores) to improve agent reliability.
• Agent observability & monitoring (AgentOps): track agent behavior, tool calls, outcomes, and quality signals; implement alerts/traces and feedback loops for continuous improvement.
• Cloud and/or platform engineering exposure for deploying agentic systems at scale (containers/Kubernetes/OpenShift, CI/CD, performance tuning, and secure operations).
• Responsible AI & guardrails: design human-in-the-loop controls, safe tool access, and security-aware policies for agents operating with credentials, data access, and budgets.
• Proficiency in programming languages such as Python, .Net or Java, with experience in relevant libraries and frameworks (e.g., TensorFlow, PyTorch, Keras).